Skip to content

LEON-gittech/Skill2Poster / academic-poster-builder

academic-poster-builder

Verified

Build, critique, and refine academic posters from a paper, LaTeX project, reference draft image, HTML/CSS source, PPT/PDF outputs, or local figure assets. Use when Codex is asked to create or improve a research poster, convert a poster design to HTML/PDF/PPTX, fix poster layout/typography/overflow/blank-space issues, or preserve paper figures and result semantics in a poster.

FileKindSize
SKILL.mdskill md8.9 KB
agents/openai.yamlconfig234 B
references/poster-qa-checklist.mdmarkdown3.9 KB

references/poster-qa-checklist.md

View on GitHub
# Poster QA Checklist

Use this checklist when refining an A0 portrait academic poster generated from HTML/CSS.

## Source Fidelity

- Confirm all key claims, metrics, and baselines against the paper.
- Prefer paper-native figures and tables over recreated approximations.
- Check that figure captions describe the mechanism or result, not just the image name.
- Remove duplicate evidence: one main table plus one concise interpretation is usually enough.

## Layout

- Header does not crowd title, authors, institution logos, or QR codes.
- Four metric cards have parallel structure: title, value, comparison.
- Thesis strip is one sentence and appears below the metric cards.
- Section order follows the poster logic and section numbering.
- Three column bottoms align or differ only by a small intentional amount.
- Each section has at least one of: a figure/table plus short explanation, or a compact evidence card.
- If a complete figure creates awkward whitespace, rebalance adjacent explanatory content before cropping or splitting the figure.
- Bottom whitespace is balanced and not caused by hidden overflow.

## Typography

- Title/subtitle hierarchy is clear but not excessively bold.
- Body text is consistent across sections.
- Captions and table text are readable without zoom.
- Figure-internal text is not smaller than surrounding body text when the figure carries the main argument.
- Section headers, metric values, and conclusion text do not use heavy weights everywhere.
- Two-digit section numbers do not overflow their badges.

## Figures and Tables

- Overview/method diagrams are placed in the wide column.
- Comparable plots are the same size.
- Equations are large enough, especially longer equations.
- Coherent figures remain complete unless the user explicitly wants a crop/split and the crop preserves context.
- Tables do not touch panel borders.
- Any chart added to fill space has a label explaining what it means.
- Redundant tables or metrics are removed instead of duplicated.

## QR and Branding

- Use source/official logos where possible.
- QR codes are large enough to scan and have captions when helpful.
- Avoid bottom metadata footers unless required.

## Playwright Measurement Snippet

Run this from the repository root after setting `NODE_PATH` to a Playwright installation if needed.

```js
const path = require("path");
const { chromium } = require("playwright");

(async () => {
  const root = path.resolve("poster_build");
  const browser = await chromium.launch({
    headless: true,
    executablePath: "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome",
  });
  const page = await browser.newPage({
    viewport: { width: 3179, height: 4494 },
    deviceScaleFactor: 1,
  });
  await page.goto(`file://${path.join(root, "poster.html")}`, { waitUntil: "load" });
  const result = await page.evaluate(() => {
    const overflows = [...document.querySelectorAll(".col > .panel")].filter((panel) => {
      const body = panel.querySelector(".panel-body");
      return (
        panel.scrollHeight > panel.clientHeight + 2 ||
        (body && body.scrollHeight > body.clientHeight + 2)
      );
    }).map((panel) => panel.querySelector(".panel-title")?.innerText.replace(/\n/g, " ").trim());

    const bottoms = [...document.querySelectorAll(".col")].map((col) =>
      Math.round(col.querySelector(".panel:last-child").getBoundingClientRect().bottom)
    );

    return {
      scrollWidth: document.body.scrollWidth,
      scrollHeight: document.body.scrollHeight,
      posterBottom: Math.round(document.querySelector(".poster").getBoundingClientRect().bottom),
      contentBottom: Math.round(document.querySelector(".content").getBoundingClientRect().bottom),
      bottoms,
      overflows,
    };
  });
  console.log(JSON.stringify(result, null, 2));
  await browser.close();
})();
```

Accept only when:

- `scrollWidth` is `3179`.
- `scrollHeight` is `4494`.
- `overflows` is empty.
- Column `bottoms` are aligned or intentionally close.
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall